Aerosol Parameters Retrieval From TROPOMI/S5P Using Physics-Based Neural Networks
In this article, we present three algorithms for aerosol parameters retrieval from TROPOspheric Monitoring Instrument measurements in the <inline-formula><tex-math notation="LaTeX">$\text {O}_{2}$</tex-math></inline-formula> A-band. These algorithms use neural netwo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9851509/ |
| _version_ | 1811308712476803072 |
|---|---|
| author | Lanlan Rao Jian Xu Dmitry S. Efremenko Diego G. Loyola Adrian Doicu |
| author_facet | Lanlan Rao Jian Xu Dmitry S. Efremenko Diego G. Loyola Adrian Doicu |
| author_sort | Lanlan Rao |
| collection | DOAJ |
| description | In this article, we present three algorithms for aerosol parameters retrieval from TROPOspheric Monitoring Instrument measurements in the <inline-formula><tex-math notation="LaTeX">$\text {O}_{2}$</tex-math></inline-formula> A-band. These algorithms use neural networks 1) to emulate the radiative transfer model and a Bayesian approach to solve the inverse problem, 2) to learn the inverse model from the synthetic radiances, and 3) to learn the inverse model from the principal-component transform of synthetic radiances. The training process is based on full-physics radiative transfer simulations. The accuracy and efficiency of the neural network based retrieval algorithms are analyzed with synthetic and real data. |
| first_indexed | 2024-04-13T09:28:12Z |
| format | Article |
| id | doaj.art-d8fc6147e68541f3be53e4ba8c399396 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-13T09:28:12Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-d8fc6147e68541f3be53e4ba8c3993962022-12-22T02:52:22ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01156473648410.1109/JSTARS.2022.31968439851509Aerosol Parameters Retrieval From TROPOMI/S5P Using Physics-Based Neural NetworksLanlan Rao0https://orcid.org/0000-0003-4439-0496Jian Xu1https://orcid.org/0000-0003-2348-125XDmitry S. Efremenko2https://orcid.org/0000-0002-7449-5072Diego G. Loyola3https://orcid.org/0000-0002-8547-9350Adrian Doicu4Remote Sensing Technology Institute, German Aerospace Center (DLR), Oberpfaffenhofen, GermanyNational Space Science Center, Chinese Academy of Sciences, Beijing, ChinaRemote Sensing Technology Institute, German Aerospace Center (DLR), Oberpfaffenhofen, GermanyRemote Sensing Technology Institute, German Aerospace Center (DLR), Oberpfaffenhofen, GermanyRemote Sensing Technology Institute, German Aerospace Center (DLR), Oberpfaffenhofen, GermanyIn this article, we present three algorithms for aerosol parameters retrieval from TROPOspheric Monitoring Instrument measurements in the <inline-formula><tex-math notation="LaTeX">$\text {O}_{2}$</tex-math></inline-formula> A-band. These algorithms use neural networks 1) to emulate the radiative transfer model and a Bayesian approach to solve the inverse problem, 2) to learn the inverse model from the synthetic radiances, and 3) to learn the inverse model from the principal-component transform of synthetic radiances. The training process is based on full-physics radiative transfer simulations. The accuracy and efficiency of the neural network based retrieval algorithms are analyzed with synthetic and real data.https://ieeexplore.ieee.org/document/9851509/Aerosol information retrievalneural networksTROPOspheric Monitoring Instrument/Sentinel-5 Precursor (TROPOMI/S5P) |
| spellingShingle | Lanlan Rao Jian Xu Dmitry S. Efremenko Diego G. Loyola Adrian Doicu Aerosol Parameters Retrieval From TROPOMI/S5P Using Physics-Based Neural Networks IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Aerosol information retrieval neural networks TROPOspheric Monitoring Instrument/Sentinel-5 Precursor (TROPOMI/S5P) |
| title | Aerosol Parameters Retrieval From TROPOMI/S5P Using Physics-Based Neural Networks |
| title_full | Aerosol Parameters Retrieval From TROPOMI/S5P Using Physics-Based Neural Networks |
| title_fullStr | Aerosol Parameters Retrieval From TROPOMI/S5P Using Physics-Based Neural Networks |
| title_full_unstemmed | Aerosol Parameters Retrieval From TROPOMI/S5P Using Physics-Based Neural Networks |
| title_short | Aerosol Parameters Retrieval From TROPOMI/S5P Using Physics-Based Neural Networks |
| title_sort | aerosol parameters retrieval from tropomi s5p using physics based neural networks |
| topic | Aerosol information retrieval neural networks TROPOspheric Monitoring Instrument/Sentinel-5 Precursor (TROPOMI/S5P) |
| url | https://ieeexplore.ieee.org/document/9851509/ |
| work_keys_str_mv | AT lanlanrao aerosolparametersretrievalfromtropomis5pusingphysicsbasedneuralnetworks AT jianxu aerosolparametersretrievalfromtropomis5pusingphysicsbasedneuralnetworks AT dmitrysefremenko aerosolparametersretrievalfromtropomis5pusingphysicsbasedneuralnetworks AT diegogloyola aerosolparametersretrievalfromtropomis5pusingphysicsbasedneuralnetworks AT adriandoicu aerosolparametersretrievalfromtropomis5pusingphysicsbasedneuralnetworks |